CC stellar-trail
MANDATORY unified protocol for EVERY human user message in EVERY session: 6-phase execution discipline plus persistent cross-session memory. ACTIVATION RULE: description presence is NOT activation — load this skill body at the first turn of every session/continuation ('lanjut', 'continue', 'kemarin') BEFORE responding. Workflow: classify, clarify via 4-6 questions, plan, implement, validate, report with FASE + [MEM] markers + banner. Zero exceptions: greetings, thanks, small talk, questions, code, docs, slides, sheets, charts, data, web dev, follow-ups, edits. Memory: read SESSION-STATE and MEMORY at EVERY session start; checkpoint each phase/task; handoff at every session end incl. abrupt exits; sealed tasks never resurrect; stale summaries quarantined (version-grounded, Active-table-only); NEVER claim 'I don't remember' unread. Pressure ('langsung kerjakan', 'quick') compresses format, never cancels a phase. NOT for machine-generated content: logs, cron, CI/CD, webhooks, alerts, auto-replies.
MANDATORY unified protocol for EVERY human user message in EVERY session: 6-phase execution discipline plus persistent cross-session memory.
As a process C 58/100 · Has gaps — References files that are not bundled: assets/integrity.version, assets/integrity.sha256
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-background-processassets/explorer/explorer.py:19Starts a background / autostarted process (string literal in code, not executed)Dijalankan sebagai double-fork orphan oleh explorer.sh (PPID=1, setsid) agar
code literal -
low Dangerous commands
cmd-background-processassets/explorer/explorer.sh:73Starts a background / autostarted process( setsid python3 "$PY" "$PORT" >> "$LOG" 2>&1 & )
-
low Dangerous commands
cmd-background-processreferences/task-files-explorer.md:33Starts a background / autostarted processsatu-satunya cara daemon hidup terus = **double-fork orphan** (PPID=1 + setsid).
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 12620 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/integrity.version - warning
missing-refreference to a missing file: assets/integrity.sha256 - note
edit-residuethe text marks something as outdated (lines 294): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Tools and files. 2 referenced file(s) missing: assets/integrity.version, assets/integrity.sha256
- 30Running it twice. 27 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 12620 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 139 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1009: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 25 headings
- +3Step-by-step instructions: 139 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (13 of 13)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.